The Varied Facets of Enabling Audio and Video Accessibility with Conversation Intelligence

by Vikram Modgil | 01-29-2022

Making audio and video content accessible can be more than just an ability to access content in ways that are convenient or feasible. The concept of making content accessible also includes modern-life time restraints so people can consume with minimal effort. Accessibility can also cover intuitive search and navigation of specific topics within audio and video faster, and the ability to moderate what you see or hear. Conversation Intelligence enables every aspect of accessibility with intelligent transcriptions, closed captions, indexing, topics, search, and summaries. Symbl.ai offers an intelligent, domain agnostic, horizontally applicable, cohesive API platform to future-proof facilitating accessibility.

What do we mean by audio and video accessibility?

When we think of audio and video content accessibility, we usually think about disabilities. For example, people with limited or no hearing can’t experience and benefit from audio. They need to consume their content in a different way. This is a huge and important area where conversation intelligence enables valuable accessibility with intelligent transcriptions and insights.

But accessibility is wider than this. It covers busy people, multitasking, accessing specific parts by identifying topics of interest, and moderating content. The full potential of enabling accessibility with conversation intelligence is concerned with facilitating a more satisfying, useful, and focused user experience.

How conversation intelligence enables audio and video accessibility

Physical impairments

If you use audio or video content without captions, people with hearing difficulties or who are deaf will miss out on your content. With over five percent of the world’s population experiencing significant hearing loss, this is a huge audience that you’re potentially excluding.

Your solution with conversation intelligence: Intelligent transcription. Because conversation intelligence listens and understands your audio content like a human, and is domain-agnostic, it can create a highly accurate transcription in real time or asynchronously from a recording.

If your industry domain is regulated, accessibility is a legal requirement. An example is EdTech, which is a regulated market with mandated accessibility compliance. In this situation, you must provide audio and video captions. 

In addition to enabling accessibility, intelligent transcriptions widen your audience, boost engagement, provide more flexibility, and create a more fulfilling user experience.

Modern-life time constraints

There can be a real-time accessibility issue with content when people are too busy in the moment. For example, when there’s a webinar at the same time as another meeting, if they can’t access the webinar later then they won’t be able to watch it and the opportunity is missed. The same is true of recorded content, like a Facebook video, which needs to capture attention in the moment or risk a viewer scrolling past. The video accessibility needed here is for effortless consumption so you don’t miss the opportunity to engage someone.

Such an audience might also want the option to multi-task. For example, if you’re in an online meeting you can’t watch and listen to a video on another screen at the same time, but you would be able to read text captions on that video. The ability to keep audio off can also give a layer of privacy. 

Your solution with conversation intelligence: Summaries. As well as highly accurate real-time and async transcriptions, you can use conversation intelligence to understand what the content is about and automatically create a short and accurate summary.  With this summary, you can grab your audience’s attention and they can quickly and easily assess whether the content is useful to them.

Intuitive search and navigation

Another definition of accessibility could relate to your audience being able to access information within long-form audio and video content. Conversational audio and video content are particularly hard to access and navigate because it contains so much free-flowing, continuous information. This can be overcome by indexing and search capabilities. 

Your solution with conversation intelligence: Indexing and Search.  With conversation intelligence, you can create automatic indexing of voice or video content. You can index by topic, using a parent-child hierarchy, or by Q&A. If you index by topic, a person will stay longer and watch or listen as they can instantly access what’s most interesting to them or they can see what topics are coming up next. With these indexed topics, you can search the content more effectively. Your audience can also bookmark and intuitively search and navigate the content that is interesting to them. These highlights mean your audience remains engaged with the content and conversations over time. This also serves to heighten awareness and recollection when a person re-consumes content at a later date.

Content moderation

“Enabling accessibility” can also mean an ability to moderate content. For example, moderation can mean you don’t see something violent or hate-related, or you receive a warning. 

The ability to moderate what you see makes your content engagement more predictable and empowers you to choose what you access. 

Your solutions with conversation intelligence: Topics and Search. You’ve probably experienced AI that can identify swear words and blank them out. This is relatively basic. But when you use conversation intelligence to its full potential, it’ll intelligently understand the topics (the main subjects talked about), index those topics, and moderate them for you. 

Once you have the topic(s) of your content and their Message IDs (the unique message identifier of the corresponding messages or sentences), then you can automatically index your long-form voice or video content and give users a flexible and easy way to navigate or search hours of recordings.

Why use an API platform like Symbl.ai for audio and video accessibility?

You have three choices:

  • Build a solution yourself, which will take time and money.
  • Use transcriptions directly from cloud providers (like GCP, AWS, or Azure)  to build a solution that’ll involve you assembling API’s and making them work together.
  • Use Symbl.ai’s API, which is a developer platform that easily adapts to your use case. Symbl.ai offers one API which will seamlessly integrate all the insights you need now and provides you with building blocks for the future, without any heavy lifting in terms of processing. You can choose what features you use. Building on speech to text with indexing, topics, sentiment analysis, summaries … whatever your business needs now and in the future.

Symbl.ai offers an intelligent, domain agnostic, horizontally applicable, cohesive API platform to future-proof facilitating accessibility. Learn more and sign up for a free account today to get started.

Additional reading:

Vikram Modgil